Intercept LLM API traffic and visualize token usage in a real-time terminal dashboard. Track costs, debug prompts, and monitor context window usage across your AI development sessions.
tokdu (Token Disk Usage) is a terminal-based utility that helps you analyze and visualize token usage in your codebase. Similar to the classic du (disk usage) command, tokdu shows you how many tokens your files and directories consume, which is essential when working with Large Language Models (LLMs) that have token limits.
Lightweight, dependency-free logging and analytics for LLM API calls — track tokens, cost, and latency to a plain JSONL file.
macOS menu bar widget that tracks Claude context window fill with research-calibrated context rot warnings. Every other tracker tells you when you'll hit your rate limit — this one tells you when Claude is getting dumber.
Tiktoken-counter as standalone API
🧮 Calculator for vision tokens in VLMs.
G4 Claw Counter — Windows desktop widget tracking AI token usage & costs across Claude Code, Claude Desktop, OpenAI Codex, and more. Zero AI tokens consumed. Shows today's cost, multi-provider support, user-editable pricing.
Real-time terminal dashboard for Ollama — live output token counting (tokens/sec), CPU & thread usage, Apple Silicon GPU utilization, VRAM and loaded models. htop for your local LLM.
Chrome extension that shows your Claude.ai 5-hour usage as a bar at the top of every page.
Designed for LLM workflows, this tool consolidates local or GitHub-hosted codebases into a single, structured document (TXT, MD, or DOCX). It preserves directory hierarchy and file integrity while providing essential AI-centric features, including token estimation, image encoding, and intelligent filtering via .gitignore.
pakem is a repository packaging system designed to convert source trees into portable artifacts for analysis, indexing, sharing, and restoration workflows.
A tiny status line for Claude Code: model, context used, per-turn token In/Out, and estimated cost (turn + session) at public API prices.
Token counting CLI and library for multiple LLM tokenizers — count tokens and estimate API costs across OpenAI, Anthropic, and open-source models
Display prompt in 75-token chunks alongside the token counter.
Python port of @mukundakatta/agentfit: fit your messages into the LLM context window
Always-visible Claude Code quota tracker. Bloomberg-terminal menu-bar widget + SQLite token forensics + pacing CLI that tells you if you'll survive the week.
Lightweight token-usage counter for Claude Code (terminal + macOS SwiftBar). Mirrors claude.ai/settings/usage.
✂️ Lightweight, framework-agnostic Python library for intelligent LLM context window management and memory heap packing. Zero dependencies.
Add a description, image, and links to the token-counter topic page so that developers can more easily learn about it.
To associate your repository with the token-counter topic, visit your repo's landing page and select "manage topics."